{"total":14,"rows":[{"id":"2403.19448","title":"Fisher-Rao Gradient Flows of Linear Programs and State-Action Natural Policy Gradients","created":"2024-03-28","cited_by_count":5,"area":"deeprl"},{"id":"2506.03757","title":"PPO in the Fisher-Rao geometry","created":"2025-06-04","cited_by_count":4,"area":"deeprl"},{"id":"2605.22622","title":"A note on convergence of Wasserstein policy optimization","created":"2026-05-21","cited_by_count":2,"area":"deeprl"},{"id":"2406.04163","title":"Optimal Rates of Convergence for Entropy Regularization in Discounted Markov Decision Processes","created":"2024-06-06","cited_by_count":1,"area":"deeprl"},{"id":"2411.19193","title":"Convex Regularization and Convergence of Policy Gradient Flows under Safety Constraints","created":"2024-11-28","cited_by_count":1,"area":"deeprl"},{"id":"2506.05894","title":"Policy Optimization for Continuous-time Linear-Quadratic Graphon Mean Field Games","created":"2025-06-06","cited_by_count":1,"area":"deeprl"},{"id":"2510.14898","title":"Convergence of an actor-critic gradient flow for entropy regularised MDPs in general spaces","created":"2025-10-16","cited_by_count":1,"area":"deeprl"},{"id":"2605.24357","title":"Refined Analysis of Entropy-Regularized Actor-Critic","created":"2026-05-23","cited_by_count":1,"area":"deeprl"},{"id":"2602.10838","title":"Mirror descent actor-critic methods for entropy regularised MDPs in general spaces: stability and convergence","created":"2026-02-11","cited_by_count":0,"area":"deeprl"},{"id":"2605.24939","title":"Global linear convergence of entropy-regularized softmax policy gradient beyond tabular MDPs","created":"2026-05-24","cited_by_count":0,"area":"deeprl"},{"id":"2606.04335","title":"Policy Gradient for Continuous-Time Robust Markov Decision Processes","created":"2026-06-03","cited_by_count":0,"area":"deeprl"},{"id":"2606.12875","title":"Randomized Optimal Switching Problem and Related Mirror Descent Flow","created":"2026-06-11","cited_by_count":0,"area":"deeprl"},{"id":"2607.03168","title":"Entropy Regularization Improves Policy Robustness in Continuous-Time Reinforcement Learning","created":"2026-07-03","cited_by_count":0,"area":"deeprl"},{"id":"2609.35466","title":"An analysis of Mirror-Descent Soft Actor-Critic","created":"2026-09-28","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}